Automatic Delineation Research Articles

Online adaptive radiotherapy for bladder cancer using a simultaneous integrated boost and fiducial markers

PurposeThe aim was to assess the feasibility of online adaptive radiotherapy (oART) for bladder cancer using a focal boost by focusing on the quality of the online treatment plan and automatic target delineation, duration of the workflow and performance in the presence of fiducial markers for tumor bed localization.MethodsFifteen patients with muscle invasive bladder cancer received daily oART with Cone Beam CT (CBCT), artificial intelligence (AI)-assisted automatic delineation of the daily anatomy and online plan reoptimization. The bladder and pelvic lymph nodes received a total dose of 40 Gy in 20 fractions, the tumor received an additional simultaneously integrated boost (SIB) of 15 Gy. The dose distribution of the reference plan was calculated for the daily anatomy, i.e. the scheduled plan. Simultaneously, a reoptimization of the plan was performed i.e. the adaptive plan. The target coverage and V95% outside the target were evaluated for both plans. The need for manual adjustments of the GTV delineation, the duration of the workflow and the influence of fiducial markers were assessed.ResultsAll 300 adaptive plans met the requirement of the CTV-coverage V95%≥98% for both the boost (55 Gy) and elective volume (40 Gy). For the scheduled plans the CTV-coverage was 53.5% and 98.5%, respectively. Significantly less tissue outside the targets received 55 Gy in case of the adaptive plans as compared to the scheduled plans. Manual corrections of the GTV were performed in 67% of the sessions. In 96% of these corrections the GTV was enlarged and resulted in a median improvement of 1% for the target coverage. The median on-couch time was 22 min. A third of the session time consisted of reoptimization of the treatment plan. Fiducial markers were visible on the CBCTs and aided the tumor localization.ConclusionsAI-driven CBCT-guided oART aided by fiducial markers is feasible for bladder cancer radiotherapy treatment including a SIB. The quality of the adaptive plans met the clinical requirements and fiducial markers were visible enabling consistent daily tumor localization. Improved automatic delineation to lower the need for manual corrections and faster reoptimization would result in shorter session time.

Development and validation of a fully automatic tissue delineation model for brain metastasis using a deep neural network.

Stereotactic radiosurgery (SRS) treatment planning requires accurate delineation of brain metastases, a task that can be tedious and time-consuming. Although studies have explored the use of convolutional neural networks (CNNs) in magnetic resonance imaging (MRI) for automatic brain metastases delineation, none of these studies have performed clinical evaluation, raising concerns about clinical applicability. This study aimed to develop an artificial intelligence (AI) tool for the automatic delineation of single brain metastasis that could be integrated into clinical practice. Data from 426 patients with postcontrast T1-weighted MRIs who underwent SRS between March 2007 and August 2019 were retrospectively collected and divided into training, validation, and testing cohorts of 299, 42, and 85 patients, respectively. Two Gamma Knife (GK) surgeons contoured the brain metastases as the ground truth. A novel 2.5D CNN network was developed for single brain metastasis delineation. The mean Dice similarity coefficient (DSC) and average surface distance (ASD) were used to assess the performance of this method. The mean DSC and ASD values were 88.34%±5.00% and 0.35±0.21 mm, respectively, for the contours generated with the AI tool based on the testing set. The DSC measure of the AI tool's performance was dependent on metastatic shape, reinforcement shape, and the existence of peritumoral edema (all P values <0.05). The clinical experts' subjective assessments showed that 415 out of 572 slices (72.6%) in the testing cohort were acceptable for clinical usage without revision. The average time spent editing an AI-generated contour compared with time spent with manual contouring was 74 vs. 196 seconds, respectively (P<0.01). The contours delineated with the AI tool for single brain metastasis were in close agreement with the ground truth. The developed AI tool can effectively reduce contouring time and aid in GK treatment planning of single brain metastasis in clinical practice.

Whole Regional Lymph Node Area Delineation with Deep Learning Model for Total Marrow and Lymphoid Irradiation.

Total body irradiation (TBI) has been performed for conditioning before hematopoietic stem cell transplantation. However, TBI can be related to diverse adverse events including radiation pneumonitis and cataract. Efforts to reduce these events include the total marrow irradiation (TMI) and total marrow and lymphoid irradiation (TMLI). Compared to TMI, TMLI requires more target delineations with lymph nodes which can be labor-intensive and time-consuming. However, with the TMI plans, the coverage to lymph node might be lower than TMLI and its clinical significance is unknown. In the current study, we aimed to develop a deep learning model for automatic delineation of whole regional lymph nodes area and assess the dose coverage of lymph nodes with TMI plans. Whole regional lymph nodes (cervical, axillary, mediastinal, para-aortic, common iliac, external iliac, internal iliac, obturator, presacral, inguinal lymph nodes) were manually contoured by 3 radiation oncologists in 26 patients having whole body computed tomography (CT) images. Twenty patients were designated as the training/validation set and 6 patients as the testing set, and model was developed using the 'nnUNET' framework. The trained model was evaluated with dice coefficient score (DCS), precision, and recall. In addition, dose coverage of the automatically or manually delineated lymph nodes in TMI plans was calculated. The mean value of DCS, precision, and recall of the trained model was 0.76, 0.81, and 0.74, respectively. Dose parameters for manually delineated lymph nodes in previously treated TMI plans showed the mean value of V100% (the percentage of volume receiving 100% of the prescribed dose), V95%, and V90% to be 46.50%, 62.12%, and 73.68%, respectively. The highest V90% was observed in presacral (93.61%), axillary (90.40%), obturator (88.78%), and internal iliac lymph nodes (84.67%). In contrast, the lowest V90% was identified in inguinal (47.95%), cervical (61.69%), and para-aortic (65.75%) and external iliac lymph nodes (68.97%). For automatically delineated lymph nodes, the mean value of V100%, V95%, and V90% of TMI plan was 38.35%, 55.06%, and 67.84%, respectively. The difference with dose coverage of lymph node between delineated manually and automatically was not statistically significant. Automatic delineation of lymph node using deep learning showed the potential to reduce the labor-intensive process of TMLI. When treated with TMI, the coverage of inguinal, cervical, para-aortic and external iliac lymph nodes was lower than expected.

Automatic urban boundary delineation in equatorial regions using SAR imagery: a comprehensive approach with decomposition, morphology, and statistical active contours

Automatic urban boundary delineation in equatorial regions using SAR imagery: a comprehensive approach with decomposition, morphology, and statistical active contours

GTV Based Automatic Delineation of Clinical Target Volume for Cervical Cancer

The delineation of gross tumor volume (GTV) and clinical target volume (CTV) are two critical steps in the radiotherapy planning for cervical cancer. GTV defines the primary treatment region for the gross tumor, while CTV is the area surrounding GTV that includes a certain probability (5% to 10%) of subclinical lesions. In contrast to GTV, CTV delineation relies on predefined and judgment-based boundaries, and the high variability among users makes this task particularly challenging. In this study, we evaluated the potential relationship between GTV and CTV and developed an automatic CTV delineation algorithm for cervical cancer based on the fusion of GTV information. We introduced position and shape constraints of GTV to improve the accuracy of CTV delineation. The GTV-Net deep learning method was used to segment the CTV images of cervical cancer. The method aimed to use the delineation results of the GTV region for one-hot coding and add human anatomy experience in the clinical field to guide the CTV segmentation. This retrospective study included 545 cervical cancer patients who received radiation therapy from June 2017 to May 2019, including postoperative and radical treatment groups. The CTV and GTV regions were manually delineated by human experts. Numerous experiments were conducted to evaluate the performance of the network. First, compared with different network architectures, the Dice similarity coefficient (DSC) and 95% Hausdorff distance (95HD) of GTV-Net were both improved. Then, we compared the GTV-Net method with two resident physicians. Our GTV-Net method outperformed both resident physicians. In the postoperative group, our method improved the DSC by 4% compared to 3D-UNet, reaching 76.55%, and increased by about 2.57% compared to V-Net's 73.98%, with an improvement of approximately 1.23% compared to the two resident physicians. In the radical treatment group, compared to 3D-UNet's 78.76%, our method increased the DSC by about 3.25%, reaching 82%, and increased by approximately 2.08% compared to V-Net's 79.92%, with an improvement of about 1.35% compared to the two resident physicians. Compared with 3D-UNet, the average 95HD in the postoperative group decreased from 1.489 to 1.457, and in the radical treatment group, it decreased from 1.454 to 1.433. The results of 95HD also showed some improvement compared to V-Net. This study is the first to introduce GTV information for automatic segmentation of the clinical target area for cervical cancer. In this experiment, we observed a positive gain in CTV target automatic delineation guided by GTV information compared to solely performing CTV segmentation, with an improvement in Dice similarity of more than 4% and Hausdorff distance of more than 6% in the experimental dataset. In addition, GTV-guided CTV automatic delineation has also shown promising results on multicenter data, which will better serve the clinical field.

Deep Learning and GAN-Synthesis for Auto-Segmentation of Pancreatic Cancer by Non-Enhanced CT for Adaptive Radiotherapy

In conventional adaptive radiotherapy (ART) for pancreatic cancer, contrast-enhanced CT (CECT) helps to more precisely delineate primary gross tumor volume (GTV) than non-enhanced CT (NECT). However, frequent use of contrast medium can damage kidneys and prolong treatment time. Moreover, traditional manual delineation is labor-intensive and highly dependent on the experience of oncologists. Currently, automatic delineation based on deep learning with Generative Adversarial Networks (GAN)-based CT synthesis is one of the most feasible solutions to these problems. A dataset of 35 pancreatic cancer patients was retrospectively collected from May 2021 to December 2022. All patients consist of a pair of NECT and CECT. We designed and developed an automatic delineation framework (Proposed) for GTV of pancreatic cancer based on Trans-cycleGAN and a modified 3D U-Net. TranscycleGAN can not only synthesize CECT from NECT, but can also augment the amount of CT images; then all real and synthesized CT images were used to train the modified 3D U-Net for automatic delineation of GTV; finally, our framework was able to automatically delineate GTV by NECT, but not only by CECT. Our framework was evaluated by dice similarity coefficient (DSC), 95% Harsdorff distance (95HD) and average surface distance (ASD) with oncologists' manual delineation ("gold standard"). The evaluation results were summarized in Table 1. The proposed framework achieved the best automatic delineation results by NECT, which was superior to that of CECT: 0.917 & 0.903 of DSC, 2.498mm & 3.029mm of HD95, 0.481mm & 0.534mm of ASD, p < 0.05 for DSC and HD95. Specifically, it is significantly superior to the automatic delineation results using U-Net by CECT 0.917 & 0.818 of DSC, 2.498mm & 13.228mm of HD95, 0.481mm & 3.633mm of ASD, p < 0.05 for DSC. We proposed an automatic delineation framework for contouring GTV in ART of pancreatic cancer based on deep learning and Trans-cycleGAN network. This framework could automatically delineate GTV and achieve better performance with NECT compared to CECT. Our method could not only reduce the use of contrast medium, but also increase the precision and effectiveness of tumor delineation, which could have a positive impact on precision radiotherapy.

Clinical prior Knowledge-Based One-Shot Learning for Automatic Delineation of Clinical Target Volumes in Adaptation Radiotherapy of Cervical Cancer

Rapid and accurate delineation of clinical target volumes (CTV) of cervical cancer is the crux to ensure the efficiency and benefits of adaptation radiotherapy (ART). However, contour propagation using deformation image registration (DIR) is difficult to ensure the accuracy of CTV contours due to the significant tumor recession in next fraction, and the tumor progress in each fraction is not considered by conventional automatic delineation methods based on deep learning (DL). Currently, one-shot learning (OSL) is feasible to learn the tumor progress from former fractions to improve the accuracy of automatically delineating CTV. We retrospectively collected 45 patients with cervical cancer from January 2021 to May 2022 in our department. All patients consist of a pair of planning CT and daily CT in ART. A personalized automatic delineation method based on one-shot learning was developed to delineate CTV in daily CT by learning the clinical prior knowledge from the CTV contours and images of planning CT. The performance of our proposed method was evaluated by dice similarity coefficient (DSC), 95% Harsdorff distance (95HD) and average surface distance (ASD) with human experts, and its automatic delineation performance were compared with DIR and DL in daily CT. Our automatic delineation method OSL performed the best results in all evaluation metrics (denoted by mean ± standard deviation) as shown in Table 1, it is superior to method DL: 0.92 & 0.90 of DSC, 2.33 mm & 2.68 mm of HD95, 0.68 mm & 0.82 mm of ASD, P < 0.05 for DSC and ASD. Specifically, our method is significantly superior to the automatic delineation results by method DIR: 0.92 & 0.84 of DSC, 2.33 mm & 4.11 mm of HD95, 0.68 mm & 1.52 mm of ASD, P < 0.05 for all. In addition, OSL can significantly overcome the delineation problems in fuzzy boundary and delineation missing and perform better generalization for some unusual images, compared with DIR and DL. We proposed an automatic delineation method based on one-shot learning for CTV of cervical cancer in ART, the results demonstrated that the proposed method could improve the precision and generalization of automatically delineating CTV compared against current popular methods. Therefore, it is potential to improve the quality and efficiency of ART for personalized patients and have a positive impact on tumor control and patient survival.

Deep Learning for Automated Contouring of Primary Gross Tumor Volumes by MRI for Radiation Therapy of Brain Metastasis

Radiotherapy is one of the most effective methods for the treatment of brain metastases (BMs). Traditional manual delineation of primary gross tumor volumes (GTV) of multiple BMs (especially small metastases) in radiotherapy practice is extremely labor intensive and highly dependent on oncologists' experience, achieving the precise and efficient automatic delineation of BMs is of great significance for efficient and homogeneous one-stop adaptive radiotherapy. We retrospectively collected 62 MRI (non-enhanced T1-weighted sequences) sequences of 50 patients with BMs from January 2020 to July 2021. An automatic model (BUC-Net) for automatic delineation BMs was proposed in this work, which was based on deep learning by combining 3D bottler layer module and the cascade architecture to improve the accuracy and efficient of BMs' automatic delineation, especially for small metastases with tiny size and relatively low contrast. The prosed method was compared with the existing 3D U-Net (U-Net) and 3D U-Net Cascade (U-Net Cascade). The performance of our proposed method was evaluated by Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and average surface distance (ASD) with human experts. The automatic segmentation results of BUC-Net evaluated with 310 BMs in 13 test patients was summarized in Table 1. These BMs in each test patient were automatically delineated by two types of contours: as a whole tumor contour (Whole-delineation) and the multiple tumor contours (Multiple-delineation). BUC-Net performed the best mean DSC and HD95, which is significantly outperformed U-Net (Whole-delineation: 0.911 & 0.894 of DSC, Multiple-delineation: 0.794 & 0.754 of DSC, P < 0.05 for both) and U-Net cascade (Whole-delineation: 0.947 & 7.141 of HD95, Multiple-delineation: 0.902 & 1.171 of HD95, P < 0.05 for both); Additionally, BUC-Net achieved the best mean ASD for Whole-delineation and comparable ASD (0.290 & 0.277, P > 0) for Multiple-delineation with U-Net Cascade. Our results showed that the proposed approach is promising for the automatic delineation of BMs in MRI, which can be integrated into a radiotherapy workflow to significantly shorten segmentation time.

Pattern Analysis of Daily Lesion Volume Trajectories for Early Prediction of Glioblastoma Progression During MR-Linac Radiotherapy

Distinguishing between true progression (TP) and pseudoprogression (PP) post-radiotherapy (RT) is of paramount importance for treatment management of patients with glioblastoma (GBM). MR-Linac systems allow for daily monitoring of tumor changes throughout the course of RT. We hypothesized that the patterns of tumor volume change during RT may enable early prediction of treatment response. Using an IRB-approved prospective cohort of GBM patients undergoing 30 fractions of chemoRT to 60 Gy on a 0.35T MR-Linac, tumor/edema (tumor lesion) regions of interest (ROI) were contoured on daily T2-weighted treatment set-up scans. The obtained tumor lesion (TL) volume changes during treatment were smoothed with a moving average Gaussian window over time. Non-negative Matrix Factorization (NMF) was applied to the data matrix D (N x F), containing the trajectories in its rows for each patient, where N is the number of patients analyzed and F is the number of fractions. NMF represents D as a linear combination of three temporal (hidden) patterns and their weights in each individual trajectory. The same analysis was performed for ΔD, containing the changes in volumes with reference to the first fraction. The calculated weights were scaled in [0, 1], expressed as probabilities (by ℓ1-normalization) and used as features in Linear Discriminant Analysis (LDA). The LDA model was trained to differentiate between no progression (NP), PP and TP, and assessed by leave-one-subject-out cross-validation. Thirty-six patients were screened for inclusion: 9 were excluded due to no T2 lesion (resection cavity only). Of the remaining 27 GBM patients analyzed, 10 had no tumor growth on first post-RT diagnostic MRI, 6 were determined to have PP based on regression or long-term stability of findings, and 11 had TP due to continued progression of disease past 6 months, rapid patient death from disease, or tissue sampling showing active malignancy. With the use of only 2 features, LDA achieved an overall accuracy of 70.4% classifying correctly: 6 (60%), 4 (67%), and 9 (82%) patients with NP, PP, and TP, respectively. The temporal NMF patterns (monotonous decrease, rapid increase during the third part of the treatment, etc.) indicate that there is enough signal to classify patients' response based on the pattern tumor volume changes during RT. We identified tumor dynamics' patterns during RT, indicative of differential behavior of tumor growth between TP and PP. Although with a limited number of patients, these initial results suggest that tumor volume changes during treatment may provide early markers of treatment response. This could allow physicians to adapt/intensify treatment in real time for poorly responding patients. Next steps include automating the process of real-time tumor volume monitoring by incorporating a deep learning solution for automatic volume delineation on daily treatment set-up scans.

Dosimetry Predictors of Late Skin Reactions after Whole Breast Radiotherapy on a Large Mono-Institutional Cohort of Patients

To develop an NTCP model predicting late skin toxicity using dosimetric parameters from the breast dermis to identify possible RT constraints on such a structure. The skin structure was defined as the 5 mm inner isotropic expansion from the outer CT body contour. It was retrospectively segmented on a large mono-Institutional cohort of early-stage breast cancer patients enrolled between 2009 and 2017 (n = 1066). Patients were treated with tangential-field RT, delivering 40 Gy in 15 fractions without a RT boost. Toxicity was reported during FU using SOMA/LENT scoring. The study endpoint was moderate-severe late toxicity consisting of Fibrosis-Atrophy-Telangiectasia-Pain (FATP G2+) developed within 42 months after RT completion. Automatic delineation of skin and DVH extraction were accomplished by scripting using the MIM_assistant software. Also, the impact of changes in the dose calculation algorithms during enrolment time was quantified. A logistic model was created by combining multifactorial variables, considering both clinical factors and the absolute skin DVH (cc). Variance Inflation Factor (VIF) was performed to reduce the multicollinearity. Repeated 5-fold cross-validation with SMOTE approach to overcome the class unbalance was applied for model feature selection. The predictive model was then developed on the entire population due to the limited G2+ events. The FATP G2+ rate was 3.8% with 40/1066 experiencing late toxicity. Among them, a 40% had already developed acute symptoms after RT completion showing a consequential effect. The multicollinearity analysis selected 27 clinical-treatment-dosimetric factors. After repeated (20 times) 5-fold cross-validation, the best-performing model included Post-Surgery Cosmetic alterations, Aromatase Inhibitors (as a protective factor), V20 Gy (50% of the prescribed dose - DVH plateau region) and V42 Gy (105% of the prescribed dose - DVH high-dose tail). Accuracy and f1-score were 0.76 and 0.58 in both training and test sets, providing good reliability for selected variables. AUC for the final model on the entire population was 0.76+/-0.04. We quantified the association between fibrosis and skin DVH when delivering 40 Gy in 15fr. The model suggested an independent role of V20 and V42 Gy and a heavy risk modulation by surgical effects and aromatase inhibitors. This last factor could interfere with adipose tissue and water-content distribution within the breast. For this purpose, a CT-based densitometry characterization of toxicity patients is ongoing.

A Multicenter Study on Deep Learning for Glioblastoma Auto-Segmentation with Prior Knowledge in Multimodal Imaging

A precise radiotherapy plan is required to ensure accurate delineation of gross tumor volumes (GTV) and clinical target volumes (CTV1 and CTV2) of glioblastomas (GBMs). However, traditional manual delineation is labor intensive and highly dependent on oncologists' experience. To construct and evaluate a deep learning-based automatic delineation method using prior knowledge in multimodal medical imaging to automate precise GTV, CTV1 and CTV2 contouring in GBM patients. We retrospectively collected the CT and MRI scans of 55 eligible patients with histologically proven high-grade glioma (HGG) from an institute, these scans were performed with non-enhanced CT (CT), contrast-enhanced T1-weighted (T1C) and T2-FLAIR (T2F) sequences. We proposed a two-stage automatic segmentation framework (PKMI-Net) for GTV, CTV1 and CTV2 based on deep learning using prior knowledge in multimodal medical imaging, and its segmentation performance was evaluated with dice similarity coefficient (DSC), 95% Harsdorff distance (HD95), average surface distance (ASD) and relative volume difference (RVD). To further investigate the generalizability of our method, we designed and conducted two evaluation strategies (Mix and Cross) on four multicenter datasets (including 55 patients, 37 patients, 21 patients and 35 patients). The evaluation results with an 11-patient test set from the single institute were summarized in Table 1, the proposed method demonstrated the best accuracy in segmenting, respectively, GTV, CTV1 and CTV, achieving a DSC of 0.94, 0.95 and 0.92; HD95 of 2.07 mm, 1.18 mm and 3.80 mm; ASD of 0.69 mm, 0.39 mm and 1.13 mm and RVE of 5.50%, 3.97% and 9.68%. In the multicenter evaluation, the segmentation performance of our method implemented with the Cross strategy was comparable to that with the Mix strategy, demonstrating that our method had high and stable generalizability across multicenter datasets in automatically segmenting GTV, CTV1 and CTV2. Our proposed method achieved promising results in automatically segmenting gliomas across various datasets, which could improve the quality and efficiency of glioblastoma radiotherapy.

Quantitative assessment of adaptive radiotherapy for prostate cancer using deep learning: Bladder dose as a decision criterion.

Adaptive radiotherapy (ART) can incorporate anatomical variations in a reoptimized treatment plan for fractionated radiotherapy. An automatic solution to objectively determine whether ART should be performed immediately after the daily image acquisition is highly desirable. We investigate a quantitative criterion for whether ART should be performed in prostate cancer radiotherapy by synthesizing pseudo-CT (sCT) images and evaluating dosimetric impact on treatment planning using deep learning approaches. Planning CT (pCT) and daily cone-beam CT (CBCT) data sets of 74 patients are used to train (60 patients) and evaluate (14 patients) a cycle adversarial generative network (CycleGAN) that performs the task of synthesizing high-quality sCT from daily CBCT. Automatic delineation (AD) of the bladder is performed on the sCT using the U-net. The combination of sCT and AD allows us to perform dose calculations based on the up-to-date bladder anatomy to determine whether the original treatment plan (ori-plan) is still applicable. For positive cases that the patients' anatomical changes and the associated dose calculations warrant re-planning, we made rapid plan revisions (re-plan) based on the ori-plan. The mean absolute error within the region-of-interests (i.e., body, bladder, fat, muscle) between the sCT and pCT are 41.2, 25.1, 26.5, and 29.0HU, respectively. Taking the calculated results of pCT doses as the standard, for PTV, the gamma passing rates of sCT doses at 1mm/1%, 2mm/2% are 87.92%, 98.78%, respectively. The Dice coefficients of the AD-contours are 0.93 on pCT and 0.91 on sCT. According to the result of dose calculation, we found when the bladder volume underwent a substantial change (79.7%), the bladder dose is still within the safe limit, suggesting it is insufficient to solely use the bladder volume change as a criterion to determine whether adaptive treatment needs to be done. After AD-contours of the bladder using sCT, there are two cases whose bladder dose . For the two cases, we perform re-planning to reduce the bladder dose to , under the condition that the PTV meets the prescribed dose. We provide a dose accurate adaptive workflow for prostate cancer patients by using deep learning approaches, and implement ART that adapts to bladder dose. Of note, the specific replanning criterion for whether ART needs to be performed can adapt to different centers' choices based on their experience and daily observations.

Breast cancer diagnosis based on hybrid SqueezeNet and improved chef-based optimizer

The most frequent disease in women and the one that accounts for the majority of cancer-related fatalities in females is breast cancer. An important milestone in breast cancer CAD systems is the automatic recognition and delineation of masses in mammograms. We have developed a novel technique in this study to identify potential mass candidates in mammograms automatically. The suggested method is a pipeline method with three stages. First, a noise reduction method based on median filtering is performed to eliminate the noises. Then, the region of interest is threshold out of the pre-processed images using the Kapur technique. Afterward, to eliminate useless features, optimum feature extraction and selection are designed. It is established by an Improved version of the Chef-Based Optimization (ICBO) algorithm. Lastly, a classification is implemented based on an optimal SqueezeNet model for the final diagnosis. This classifier is also optimized based on the ICBO algorithm to maximize efficiency. Simulations of the method are applied to the MIAS database, and its results are compared with different state-of-the-art methods to show the method's advantage.

Clinical evaluation on automatic segmentation results of convolutional neural networks in rectal cancer radiotherapy.

Image segmentation can be time-consuming and lacks consistency between different oncologists, which is essential in conformal radiotherapy techniques. We aimed to evaluate automatic delineation results generated by convolutional neural networks (CNNs) from geometry and dosimetry perspectives and explore the reliability of these segmentation tools in rectal cancer. Forty-seven rectal cancer cases treated from February 2018 to April 2019 were randomly collected retrospectively in our cancer center. The oncologists delineated regions of interest (ROIs) on planning CT images as the ground truth, including clinical target volume (CTV), bladder, small intestine, and femoral heads. The corresponding automatic segmentation results were generated by DeepLabv3+ and ResUNet, and we also used Atlas-Based Autosegmentation (ABAS) software for comparison. The geometry evaluation was carried out using the volumetric Dice similarity coefficient (DSC) and surface DSC, and critical dose parameters were assessed based on replanning optimized by clinically approved or automatically generated CTVs and organs at risk (OARs), i.e., the Planref and Plantest. Pearson test was used to explore the correlation between geometric metrics and dose parameters. In geometric evaluation, DeepLabv3+ performed better in DCS metrics for the CTV (volumetric DSC, mean = 0.96, P< 0.01; surface DSC, mean = 0.78, P< 0.01) and small intestine (volumetric DSC, mean = 0.91, P< 0.01; surface DSC, mean = 0.62, P< 0.01), ResUNet had advantages in volumetric DSC of the bladder (mean = 0.97, P< 0.05). For critical dose parameters analysis between Planref and Plantest, there was a significant difference for target volumes (P< 0.01), and no significant difference was found for the ResUNet-generated small intestine (P > 0.05). For the correlation test, a negative correlation was found between DSC metrics (volumetric, surface DSC) and dosimetric parameters (δD95, δD95, HI, CI) for target volumes (P< 0.05), and no significant correlation was found for most tests of OARs (P > 0.05). CNNs show remarkable repeatability and time-saving in automatic segmentation, and their accuracy also has a certain potential in clinical practice. Meanwhile, clinical aspects, such as dose distribution, may need to be considered when comparing the performance of auto-segmentation methods.

Automatic Extraction of Watershed Model by using Python Programming

In earlier days, watershed delineation was mainly conducted by the method of hand delineation. Now a days GIS tools are being widely used for delineation of watershed boundary and identifying stream network. The advancements and new techniques in information technologies are making it possible to acquire large-scale spatial data through satellite data, elevation models with help of user-friendly programming. Watershed delineation is a process for creating a boundary that represents the contributing area for a specific control point or water outlet, with the intent of characterization and analysis of portions of a study area. Although many GIS tools and software are available for watershed analysis, there is a need for optimized libraries for client-side and for better illustration of data in interactive environment for hydrological data analysis. In this connection, presently we are developing a model for the automatic delineation of watershed area from Shuttle Radar Topographical Mission (SRTM) digital elevation model by using Python program. The data required by the model are digital elevation and the spatial coordinate of spill way, outlets etc. In this project, we can be developed and demonstrated several watershed delineation techniques on large scale by using Python programming.

Fast Computational Approaches to Derive Fractional Pressure Ratio in Patients with Extracranial or Intracranial Symptomatic Stenosis

We aimed to evaluate the performance of fast and straightforward μQFR computation in cerebrovascular stenosis lesions. A total of 30 patients with symptomatic stenosis lesions of 50-70% luminal stenosis and underwent FPR assessment at our hospital were included in this study. μQFR was applied to the interrogated vessel. An artificial intelligence algorithm was proposed for automatic delineation of lumen contours of cerebrovascular stenosis. We used invasive fractional pressure ratios (FPRs) as a reference standard. Pearson's correlation coefficient (r) was used to assess the correlation strength between μQFR and FPR, while Bland-Altman plots were used to evaluate the agreement between μQFR and FPR. An analysis of receiver-operating characteristics (ROC) was used to evaluate the performance of μQFR. Our result displayed strong positive correlations (r = 0.92; p<0.001) between μQFR and pressure wire FPR. An excellent agreement was observed between μQFR and FPR with a mean difference of 0.01 + 0.08; p=0.263; range from -0.16 to 0.14. The overall accuracy for identifying an FPR of <0.7 was 92% (95% CI: 85% to 100%). The area under the receiver-operating characteristic curve was higher for μQFR (0.92 [95% CI: 0.81 to 0.98]) than diameter stenosis (DS) (0.88 [95% CI: 0.75 to 0.95]. The positive likelihood ratio was 3.9 for μQFR with a negative likelihood ratio of 0, respectively. The μQFR computation has a strong correlation and agrees with the FPR calculated from the pressure wire. Therefore, μQFR may provide an essential therapeutic aid in patients with symptomatic stenosis lesions.

Automatic Deep Learning-Based Pipeline for Automatic Delineation and Measurement of Fetal Brain Structures in Routine Mid-Trimester Ultrasound Images

Introduction: The aim of this study was to develop a pipeline using state-of-the-art deep learning methods to automatically delineate and measure several of the most important brain structures in fetal brain ultrasound (US) images. Methods: The dataset was composed of 5,331 images of the fetal brain acquired during the routine mid-trimester US scan. Our proposed pipeline automatically performs the following three steps: brain plane classification (transventricular, transthalamic, or transcerebellar plane); brain structures delineation (9 different structures); and automatic measurement (from the structure delineations). The methods were trained on a subset of 4,331 images and each step was evaluated on the remaining 1,000 images. Results: Plane classification reached 98.6% average class accuracy. Brain structure delineation obtained an average pixel accuracy higher than 96% and a Jaccard index higher than 70%. Automatic measurements get an absolute error below 3.5% for the four standard head biometries (head circumference, biparietal diameter, occipitofrontal diameter, and cephalic index), 9% for transcerebellar diameter, 12% for cavum septi pellucidi ratio, and 26% for Sylvian fissure operculization degree. Conclusions: The proposed pipeline shows the potential of deep learning methods to delineate fetal head and brain structures and obtain automatic measures of each anatomical standard plane acquired during routine fetal US examination.

A deep learning approach for automatic tumor delineation in stereotactic radiotherapy for non-small cell lung cancer using diagnostic PET-CT and planning CT.

Accurate delineation of tumor targets is crucial for stereotactic body radiation therapy (SBRT) for non-small cell lung cancer (NSCLC). This study aims to develop a deep learning-based segmentation approach to accurately and efficiently delineate NSCLC targets using diagnostic PET-CT and SBRT planning CT (pCT). The diagnostic PET was registered to pCT using the transform matrix from registering diagnostic CT to the pCT. We proposed a 3D-UNet-based segmentation method to segment NSCLC tumor targets on dual-modality PET-pCT images. This network contained squeeze-and-excitation and Residual blocks in each convolutional block to perform dynamic channel-wise feature recalibration. Furthermore, up-sampling paths were added to supplement low-resolution features to the model and also to compute the overall loss function. The dice similarity coefficient (DSC), precision, recall, and the average symmetric surface distances were used to assess the performance of the proposed approach on 86 pairs of diagnostic PET and pCT images. The proposed model using dual-modality images was compared with both conventional 3D-UNet architecture and single-modality image input. The average DSC of the proposed model with both PET and pCT images was 0.844, compared to 0.795 and 0.827, when using 3D-UNet and nnUnet. It also outperformed using either pCT or PET alone with the same network, which had DSC of 0.823 and 0.732, respectively. Therefore, our proposed segmentation approach is able to outperform the current 3D-UNet network with diagnostic PET and pCT images. The integration of two image modalities helps improve segmentation accuracy.

A Survey on Automatic Delineation of Radiotherapy Target Volume based on Machine Learning

ABSTRACTRadiotherapy is one of the main treatment methods for cancer, and the delineation of the radiotherapy target area is the basis and premise of precise treatment. Artificial intelligence technology represented by machine learning has done a lot of research in this area, improving the accuracy and efficiency of target delineation. This article will review the applications and research of machine learning in medical image matching, normal organ delineation and treatment target delineation according to the procudures of doctors to delineate the target volume, and give an outlook on the development prospects.

Monitoring Individual Tree Phenology in a Multi-Species Forest Using High Resolution UAV Images

Monitoring tree phenology is important for understanding ecosystem functioning and for assessing ecosystem responses to climate change. Satellite imagery offers open-access global coverage but is restricted to forest-level analyses, due to its coarse spatial resolution. Unmanned aerial vehicle (UAV) imagery can monitor phenology at the individual tree level by utilizing a centimeter-scale resolution. Two research objectives were identified for this study: (1) to derive phenological metrics at the individual tree level, using various vegetation indices (VIs); and (2) to assess the accuracy of automatic crown delineation in a diverse ecosystem. To achieve this, fourteen multi-spectral UAV flights were performed, and the ability of the normalized difference vegetation index (NDVI), enhanced vegetation index 2 (EVI2), optimized soil-adjusted vegetation index (OSAVI), and chlorophyll index red-edge (CIre) to model seasonal phenology was assessed. A double logistic model was fitted on the VI observations for each individual tree, to derive the start of season (SOS) and end of season (EOS). Individual tree crowns were delineated automatically using marker-controlled watershed segmentation (MCWS), and the treetops were identified using a local maximum filter (LMF). Overall, the automatic segmentation performed well (F-score: 0.79, IoU: 0.58), with higher accuracies in single-species areas, while it underperformed in complex mixed forest structures. All VIs captured a strong seasonal signal for the deciduous trees and derived SOS and EOS estimates consistent with literature and ground observations. General phenological patterns included an early silver birch SOS, a quick beech budburst, and large within-species phenology variations for oak trees. Seasonal VI variation for coniferous evergreen trees was limited, and the resulting phenology estimates proved unreliable. In conclusion, these findings emphasize the capabilities of UAV imagery for individual tree crown phenology monitoring. However, they also show the difficulty of monitoring evergreen phenology with the commonly-used VIs and stress the need for further investigations.